blitzreels-caption-themes
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is focused on caption theme management and interacts only with vendor-controlled API endpoints. No malicious code or unauthorized access patterns were observed.
- [PROMPT_INJECTION]: The skill processes user descriptions to create theme configurations, which is an indirect prompt injection surface.
- Ingestion points: User's natural language descriptions of theme designs in
SKILL.md. - Boundary markers: The instructions do not provide specific delimiters for segregating untrusted user input.
- Capability inventory: The generated style settings are transmitted to the
/caption-themesand/caption-themes/previewAPI endpoints. - Sanitization: No explicit input validation or sanitization requirements are described in the instructions.
Audit Metadata